Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.9472. Min Act: -0.1700
Data Index: 6104162 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.8847. Min Act: -0.1700
Data Index: 5900353 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.8847. Min Act: -0.1700
Data Index: 8729447 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6972. Min Act: -0.1700
Data Index: 2371471 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6347. Min Act: -0.1700
Data Index: 1873807 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6347. Min Act: -0.1700
Data Index: 6499393 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6347. Min Act: -0.1700
Data Index: 5493988 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6347. Min Act: -0.1700
Data Index: 5508845 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5722. Min Act: -0.1700
Data Index: 4474661 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.6347. Min Act: -0.1700
Data Index: 3151487 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5722. Min Act: -0.1700
Data Index: 1860466 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5097. Min Act: -0.1700
Data Index: 339886 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5097. Min Act: -0.1700
Data Index: 1328412 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.4472. Min Act: -0.1700
Data Index: 1267413 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5097. Min Act: -0.1700
Data Index: 3072888 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5097. Min Act: -0.1700
Data Index: 6618985 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.4472. Min Act: -0.1700
Data Index: 204007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.4472. Min Act: -0.1700
Data Index: 3245776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.5097. Min Act: -0.1700
Data Index: 5463355 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9472. Min Range: -11.9472
Max Act: 11.4472. Min Act: -0.1700
Data Index: 3000926 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19